Checks on testing

library(covid19census)
library(dplyr)

Attaching package: ‘dplyr’

The following objects are masked from ‘package:stats’:

    filter, lag

The following objects are masked from ‘package:base’:

    intersect, setdiff, setequal, union

library(tidyr)
library(ggplot2)
library(broom)
library(psych)

Attaching package: ‘psych’

The following objects are masked from ‘package:ggplot2’:

    %+%, alpha

library(stringr)
library(DataExplorer)

Registered S3 method overwritten by 'data.table':
  method           from
  print.data.table     
Registered S3 methods overwritten by 'htmltools':
  method               from         
  print.html           tools:rstudio
  print.shiny.tag      tools:rstudio
  print.shiny.tag.list tools:rstudio
Registered S3 method overwritten by 'htmlwidgets':
  method           from         
  print.htmlwidget tools:rstudio

library(plotly)

Attaching package: ‘plotly’

The following object is masked from ‘package:ggplot2’:

    last_plot

The following object is masked from ‘package:stats’:

    filter

The following object is masked from ‘package:graphics’:

    layout

theme_set(theme_bw())

t_us <-  covid19census::getus_tests()

Data of tests up to 2020-04-23 successfully imported!

names(t_us)

 [1] "date"                  "state"                 "abbr"                 
 [4] "positive"              "negative"              "pending"              
 [7] "hospitalized_curr"     "hospitalized_cumul"    "icu_curr"             
[10] "icu_cumul"             "ventilator_curr"       "ventilator_cumul"     
[13] "recovered"             "hash"                  "date_checked"         
[16] "death"                 "fips"                  "death_increase"       
[19] "hospitalized_increase" "negative_increase"     "positive_increase"    
[22] "total_test_increase"  

t_us %>% 
  select(date, state, positive, negative, pending) %>% 
  pivot_longer(cols = c("positive", "negative", "pending"), names_to = "det_tests") %>% 
  
  ggplot(aes(date, log2(value), colour = det_tests)) +
    geom_line() +
    facet_wrap(vars(state)) +
    scale_x_date(guide = guide_axis(check.overlap = TRUE, angle = 45)) +
    theme(legend.position = "top",
        legend.title = element_blank()) 

NA
NA
NA

WHO ratio positive/total to talk about reopening

t_us %>% 
  mutate(ratio_pos = positive/(positive + negative)) %>% 
  filter(date == max(date)) %>% 
  
  ggplot(aes(reorder(state, ratio_pos), ratio_pos)) +
    geom_col() +
    scale_x_discrete(guide = guide_axis(check.overlap = TRUE, angle = 90)) +
    labs(x = NULL,
         y = "positive/(positive + negative)",
         title = "Probability of a positive test") +
    theme(legend.position = "top",
        legend.title = element_blank())

t_us %>%
  select(date,
         state,
         hospitalized_curr,
         hospitalized_cumul
         # icu_curr,
         # icu_cumul
         
         ) %>%
  pivot_longer(
    cols = c(
      "hospitalized_curr",
      "hospitalized_cumul"
      # "icu_curr",
      # "icu_cumul"
    ),
    names_to = "det_tests"
  ) %>%
  
  ggplot(aes(date, log2(value), colour = det_tests)) +
  geom_line() +
  facet_wrap(vars(state)) +
  scale_x_date(guide = guide_axis(check.overlap = TRUE, angle = 45)) +
  theme(legend.position = "top",
        legend.title = element_blank())

Same states have hospitalized current but not hospitalized cumulative and vicevera ????

** Possible different meaning of variables depending on the state **

t_us %>%
  select(date,
         state,
         # hospitalized_curr,
         # hospitalized_cumul
         # icu_curr,
         # icu_cumul
         "ventilator_curr",
         "ventilator_cumul"
         
         ) %>%
  pivot_longer(
    cols = c(
      # "hospitalized_curr",
      # "hospitalized_cumul"
        "ventilator_curr",
         "ventilator_cumul"
    ),
    names_to = "det_tests"
  ) %>%
  
  ggplot(aes(date, log2(value), colour = det_tests)) +
  geom_line() +
  facet_wrap(vars(state)) +
  scale_x_date(guide = guide_axis(check.overlap = TRUE, angle = 45)) +
  theme(legend.position = "top",
        legend.title = element_blank())

t_us %>%
  select(date,
         state,
         # hospitalized_curr,
         # hospitalized_cumul
         icu_curr,
         icu_cumul
         
         ) %>%
  pivot_longer(
    cols = c(
      # "hospitalized_curr",
      # "hospitalized_cumul"
      "icu_curr",
      "icu_cumul"
    ),
    names_to = "det_tests"
  ) %>%
  
  ggplot(aes(date, log2(value), colour = det_tests)) +
  geom_line() +
  facet_wrap(vars(state)) +
  scale_x_date(guide = guide_axis(check.overlap = TRUE, angle = 45)) +
  theme(legend.position = "top",
        legend.title = element_blank())

Lets see some totals

ggplotly(
t_us %>% 
  filter(date == max(date)) %>% 
  select(-hash, -date_checked, -fips) %>%
  pivot_longer(cols = positive:total_test_increase, names_to = "metric", values_to = "value") %>% 
  ggplot(aes(state, value)) +
    geom_col() +
    facet_wrap(vars(metric), scales = "free_y", ncol = 1) + 
    scale_x_discrete(guide = guide_axis( angle = 90)),
    height = 2000,
    width = 600
)

NA